===========
fairseq2.nn
===========

.. automodule:: fairseq2
   :no-members:
   
The neural network module provides building blocks and utilities for creating
transformer-based models and other neural network architectures. It includes
the unified batch layout system, core neural network layers, and various
utilities for efficient neural network operations.

* :doc:`/reference/fairseq2.nn.batch_layout`
* :doc:`/reference/fairseq2.nn.embedding`
* :doc:`/reference/fairseq2.nn.position_encoder`
* :doc:`/reference/fairseq2.nn.normalization`
* :doc:`/reference/fairseq2.nn.projection`
* :doc:`/reference/fairseq2.nn.residual`
* :doc:`/reference/fairseq2.nn.incremental_state`
* :doc:`/reference/fairseq2.nn.utils`


See Also
--------

* :doc:`/reference/fairseq2.models` - Pre-trained model architectures
* :doc:`/reference/fairseq2.data` - Data processing pipelines